{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:H5U7WANXQED4VJAZ6BGR5HS5V5","short_pith_number":"pith:H5U7WANX","schema_version":"1.0","canonical_sha256":"3f69fb01b78107caa419f04d1e9e5daf557be08fe270738590eee384e02dac8f","source":{"kind":"arxiv","id":"2410.03298","version":1},"attestation_state":"computed","paper":{"title":"Textless Streaming Speech-to-Speech Translation using Semantic Speech Tokens","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Christian Fuegen, Duc Le, Egor Lakomkin, Jinzheng Zhao, Katerina Zmolikova, Niko Moritz, Ruiming Xie, Yashesh Gaur, Zeeshan Ahmed, Zhiping Xiu","submitted_at":"2024-10-04T10:21:15Z","abstract_excerpt":"Cascaded speech-to-speech translation systems often suffer from the error accumulation problem and high latency, which is a result of cascaded modules whose inference delays accumulate. In this paper, we propose a transducer-based speech translation model that outputs discrete speech tokens in a low-latency streaming fashion. This approach eliminates the need for generating text output first, followed by machine translation (MT) and text-to-speech (TTS) systems. The produced speech tokens can be directly used to generate a speech signal with low latency by utilizing an acoustic language model "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2410.03298","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-04T10:21:15Z","cross_cats_sorted":[],"title_canon_sha256":"f6acb4b5c200d05c7cb6d8427a318240bb2e17fab27f43886127a7907a716f4a","abstract_canon_sha256":"0b14350d5e648201cd421e4d7b425d257c513ac92c7ec32abcb3645bd6ba7ffe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:47.353957Z","signature_b64":"IUhwdUPb2iiurvQEEqWLChVa0JUEKmMxt/46a8xqdCVZ+wanOqA+jyLRY/nDNbwedC7m6i/cwwVItfmw/BxXDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f69fb01b78107caa419f04d1e9e5daf557be08fe270738590eee384e02dac8f","last_reissued_at":"2026-07-05T09:15:47.353442Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:47.353442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Textless Streaming Speech-to-Speech Translation using Semantic Speech Tokens","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Christian Fuegen, Duc Le, Egor Lakomkin, Jinzheng Zhao, Katerina Zmolikova, Niko Moritz, Ruiming Xie, Yashesh Gaur, Zeeshan Ahmed, Zhiping Xiu","submitted_at":"2024-10-04T10:21:15Z","abstract_excerpt":"Cascaded speech-to-speech translation systems often suffer from the error accumulation problem and high latency, which is a result of cascaded modules whose inference delays accumulate. In this paper, we propose a transducer-based speech translation model that outputs discrete speech tokens in a low-latency streaming fashion. This approach eliminates the need for generating text output first, followed by machine translation (MT) and text-to-speech (TTS) systems. The produced speech tokens can be directly used to generate a speech signal with low latency by utilizing an acoustic language model "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03298","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.03298/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2410.03298","created_at":"2026-07-05T09:15:47.353512+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.03298v1","created_at":"2026-07-05T09:15:47.353512+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03298","created_at":"2026-07-05T09:15:47.353512+00:00"},{"alias_kind":"pith_short_12","alias_value":"H5U7WANXQED4","created_at":"2026-07-05T09:15:47.353512+00:00"},{"alias_kind":"pith_short_16","alias_value":"H5U7WANXQED4VJAZ","created_at":"2026-07-05T09:15:47.353512+00:00"},{"alias_kind":"pith_short_8","alias_value":"H5U7WANX","created_at":"2026-07-05T09:15:47.353512+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.03382","citing_title":"High-Fidelity Simultaneous Speech-To-Speech Translation","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H5U7WANXQED4VJAZ6BGR5HS5V5","json":"https://pith.science/pith/H5U7WANXQED4VJAZ6BGR5HS5V5.json","graph_json":"https://pith.science/api/pith-number/H5U7WANXQED4VJAZ6BGR5HS5V5/graph.json","events_json":"https://pith.science/api/pith-number/H5U7WANXQED4VJAZ6BGR5HS5V5/events.json","paper":"https://pith.science/paper/H5U7WANX"},"agent_actions":{"view_html":"https://pith.science/pith/H5U7WANXQED4VJAZ6BGR5HS5V5","download_json":"https://pith.science/pith/H5U7WANXQED4VJAZ6BGR5HS5V5.json","view_paper":"https://pith.science/paper/H5U7WANX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.03298&json=true","fetch_graph":"https://pith.science/api/pith-number/H5U7WANXQED4VJAZ6BGR5HS5V5/graph.json","fetch_events":"https://pith.science/api/pith-number/H5U7WANXQED4VJAZ6BGR5HS5V5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H5U7WANXQED4VJAZ6BGR5HS5V5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H5U7WANXQED4VJAZ6BGR5HS5V5/action/storage_attestation","attest_author":"https://pith.science/pith/H5U7WANXQED4VJAZ6BGR5HS5V5/action/author_attestation","sign_citation":"https://pith.science/pith/H5U7WANXQED4VJAZ6BGR5HS5V5/action/citation_signature","submit_replication":"https://pith.science/pith/H5U7WANXQED4VJAZ6BGR5HS5V5/action/replication_record"}},"created_at":"2026-07-05T09:15:47.353512+00:00","updated_at":"2026-07-05T09:15:47.353512+00:00"}